© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106929
    Prev
    Next
    INDEX
    Explanations

    JavaScript import statements and their syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fragistics
    -0.08
    ifton
    -0.07
     nomine
    -0.07
    imon
    -0.07
    alous
    -0.06
     Lage
    -0.06
     Bold
    -0.06
    emonic
    -0.06
    ksen
    -0.06
    porn
    -0.06
    POSITIVE LOGITS
     mere
    0.07
    ãĥ¼ãĥĬ
    0.06
     respir
    0.06
    owitz
    0.06
    Dam
    0.06
     Catalyst
    0.06
    .interfaces
    0.06
    react
    0.06
     полÑĥ
    0.06
     NSObject
    0.06
    Activations Density 0.001%

    No Known Activations